Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical/legal jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NT
    -0.07
    .Pending
    -0.07
     compound
    -0.07
    "N
    -0.07
     вихов
    -0.06
     Returning
    -0.06
    ратно
    -0.06
    accine
    -0.06
    ,F
    -0.06
     returns
    -0.06
    POSITIVE LOGITS
     Loud
    0.07
    editary
    0.06
    male
    0.06
    DEV
    0.06
    ựa
    0.06
    鱼
    0.06
     Taste
    0.06
     현대
    0.06
     الشر
    0.06
     คร
    0.06
    Act Density 0.000%

    No Known Activations